Ltxvideo Disney

🚀 ltxvideo-disney

This project is a LyCORIS adapter derived from Lightricks/LTX-Video. It is designed to generate black - and - white Disney - style video scenes, offering a unique visual experience for text - to - video tasks.

🚀 Quick Start

This is a LyCORIS adapter derived from Lightricks/LTX-Video.

The main validation prompt used during training was:

A black and white disney scene in the style of Steamboat Willie

✨ Features

• Disney - Style Generation: Capable of generating black - and - white Disney - style video scenes in the style of Steamboat Willie.
• Customizable Inference: Allows users to adjust various parameters during inference, such as CFG, steps, sampler, etc.

📦 Installation

No specific installation steps are provided in the original README.

💻 Usage Examples

Basic Usage

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights


def download_adapter(repo_id: str):
    import os
    from huggingface_hub import hf_hub_download
    adapter_filename = "pytorch_lora_weights.safetensors"
    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
    os.makedirs(path_to_adapter, exist_ok=True)
    hf_hub_download(
        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
    )

    return path_to_adapter_file
    
model_id = 'Lightricks/LTX-Video'
adapter_repo_id = 'bghira/ltxvideo-disney'
adapter_filename = 'pytorch_lora_weights.safetensors'
adapter_file_path = download_adapter(repo_id=adapter_repo_id)
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

prompt = "A black and white disney scene in the style of Steamboat Willie"
negative_prompt = 'ugly, cropped, blurry, low-quality, mediocre average'

## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=25,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=768,
    height=512,
    guidance_scale=3.8,
).frames[0]

from diffusers.utils.export_utils import export_to_gif
export_to_gif(model_output, "output.gif", fps=25)

📚 Documentation

Validation settings

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

{
    "bypass_mode": true,
    "algo": "lokr",
    "multiplier": 1.0,
    "full_matrix": true,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 4,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "FeedForward": {
                "factor": 4
            },
            "Attention": {
                "factor": 2
            }
        }
    }
}